-
-
Notifications
You must be signed in to change notification settings - Fork 44
Add multi-control functionality #1380
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Add CRZ, MCX, MCZ, MCRZ functionality to ZX package.
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
📝 WalkthroughSummary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings. WalkthroughAdded multi-control ZX-diagram construction routines (CCZ, CRZ, MCRZ, MCX, MCZ), integrated them into operation parsing and transformability checks, and expanded tests to validate multi-control constructions and reductions. (≤50 words) Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/zx/FunctionalityConstruction.cpp (1)
872-896: Remove unreachable return statement.The transformability checks correctly reflect the expanded multi-control support for RZ operations. However, line 896 contains an unreachable
return false;statement since the preceding conditions exhaust all cases.Apply this diff to remove the dead code:
case qc::OpType::RZ: return true; default: return false; } - return false; } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (3)
include/mqt-core/zx/FunctionalityConstruction.hpp(1 hunks)src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (5)
📓 Common learnings
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
test/zx/test_zx_functionality.cppinclude/mqt-core/zx/FunctionalityConstruction.hppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
include/mqt-core/zx/FunctionalityConstruction.hppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🧬 Code graph analysis (2)
test/zx/test_zx_functionality.cpp (2)
include/mqt-core/zx/FunctionalityConstruction.hpp (2)
qc(39-39)qc(50-50)src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(787-804)buildFunctionality(787-788)
src/zx/FunctionalityConstruction.cpp (2)
src/zx/Rational.cpp (1)
PiRational(21-45)src/ir/operations/OpType.cpp (2)
toString(21-35)toString(21-21)
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
src/zx/FunctionalityConstruction.cpp
[warning] 388-388: src/zx/FunctionalityConstruction.cpp:388:13 [cppcoreguidelines-init-variables]
variable 'anc' is not initialized
[warning] 384-384: src/zx/FunctionalityConstruction.cpp:384:50 [clang-diagnostic-sign-conversion]
implicit conversion changes signedness: 'size_t' (aka 'unsigned long') to 'difference_type' (aka 'long')
[warning] 384-384: src/zx/FunctionalityConstruction.cpp:384:50 [bugprone-narrowing-conversions]
narrowing conversion from 'size_t' (aka 'unsigned long') to signed type 'difference_type' (aka 'long') is implementation-defined
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:67 [clang-diagnostic-sign-conversion]
implicit conversion changes signedness: 'size_t' (aka 'unsigned long') to 'difference_type' (aka 'long')
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:67 [bugprone-narrowing-conversions]
narrowing conversion from 'size_t' (aka 'unsigned long') to signed type 'difference_type' (aka 'long') is implementation-defined
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:5 [misc-const-correctness]
variable 'first' of type 'std::vector' (aka 'vector') can be declared 'const'
[warning] 382-382: src/zx/FunctionalityConstruction.cpp:382:5 [misc-const-correctness]
variable 'half' of type 'size_t' (aka 'unsigned long') can be declared 'const'
[warning] 356-356: src/zx/FunctionalityConstruction.cpp:356:5 [misc-const-correctness]
variable 'nextControl' of type 'Qubit' (aka 'int') can be declared 'const'
[warning] 339-339: src/zx/FunctionalityConstruction.cpp:339:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
[warning] 336-336: src/zx/FunctionalityConstruction.cpp:336:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
🔇 Additional comments (7)
include/mqt-core/zx/FunctionalityConstruction.hpp (1)
116-127: LGTM!The new method declarations for multi-control gates are well-structured and follow the existing API patterns. The signatures are clear and properly typed.
test/zx/test_zx_functionality.cpp (1)
232-359: Excellent test coverage for multi-control operations.The new tests thoroughly validate the multi-control functionality with:
- CRZ decomposition equivalence
- Multi-control X with varying control counts (0, 1, 3)
- Multi-control RZ with phase cancellation
- Edge cases for boundary conditions
All tests properly verify identity preservation, zero global phase, and connectivity after reduction.
src/zx/FunctionalityConstruction.cpp (5)
310-330: LGTM!The
addCczimplementation correctly decomposes the CCZ gate using the standard pattern with CNOTs, Z-spiders with appropriate phases, and Hadamard edges. The decomposition is consistent with ZX-calculus conventions.
332-340: LGTM!The
addCrzimplementation uses the correct decomposition for controlled-RZ gates. The argument order inaddCnot(diag, target, control, qubits)is intentional and follows the standard CRZ decomposition pattern where the roles are reversed.Note: The static analysis warning about swapped arguments at lines 336 and 339 is a false positive.
680-682: LGTM!The addition of the RZ case for single-control, single-target operations correctly routes to
addCrz, expanding the supported gate set.
723-740: LGTM!The updates to the two-control branch correctly:
- Build the controls vector from the operation
- Route CCZ operations to
addCcz- Route multi-controlled RZ operations to
addMcrz- Update error messages to reflect multi-control support
741-762: LGTM!The new multi-control branch properly handles operations with arbitrary numbers of controls and a single target. The routing to
addMcx,addMcz, andaddMcrzis correct and extends the ZX functionality to support general multi-controlled gates.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/zx/FunctionalityConstruction.cpp (1)
872-896: LGTM: Extended transformableToZX for controlled RZ.The updates correctly mark controlled-RZ operations as transformable in all control-count branches (1, 2, and N controls).
Minor cleanup - Line 896 has an unreachable return statement:
} else if (op->getNtargets() == 1) { switch (op->getType()) { case qc::OpType::X: case qc::OpType::Z: case qc::OpType::RZ: return true; default: return false; } - return false; } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (3)
include/mqt-core/zx/FunctionalityConstruction.hpp(1 hunks)src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (4)
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cppinclude/mqt-core/zx/FunctionalityConstruction.hpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🧬 Code graph analysis (1)
src/zx/FunctionalityConstruction.cpp (1)
include/mqt-core/zx/FunctionalityConstruction.hpp (18)
diag(65-68)diag(69-72)diag(74-76)diag(77-78)diag(80-82)diag(83-85)diag(86-87)diag(88-89)diag(91-93)diag(95-97)diag(99-101)diag(102-103)diag(105-108)diag(110-113)diag(114-115)diag(116-117)op(60-60)op(135-135)
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
src/zx/FunctionalityConstruction.cpp
[warning] 388-388: src/zx/FunctionalityConstruction.cpp:388:13 [cppcoreguidelines-init-variables]
variable 'anc' is not initialized
[warning] 384-384: src/zx/FunctionalityConstruction.cpp:384:50 [clang-diagnostic-sign-conversion]
implicit conversion changes signedness: 'size_t' (aka 'unsigned long') to 'difference_type' (aka 'long')
[warning] 384-384: src/zx/FunctionalityConstruction.cpp:384:50 [bugprone-narrowing-conversions]
narrowing conversion from 'size_t' (aka 'unsigned long') to signed type 'difference_type' (aka 'long') is implementation-defined
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:67 [clang-diagnostic-sign-conversion]
implicit conversion changes signedness: 'size_t' (aka 'unsigned long') to 'difference_type' (aka 'long')
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:67 [bugprone-narrowing-conversions]
narrowing conversion from 'size_t' (aka 'unsigned long') to signed type 'difference_type' (aka 'long') is implementation-defined
[warning] 383-383: src/zx/FunctionalityConstruction.cpp:383:5 [misc-const-correctness]
variable 'first' of type 'std::vector' (aka 'vector') can be declared 'const'
[warning] 382-382: src/zx/FunctionalityConstruction.cpp:382:5 [misc-const-correctness]
variable 'half' of type 'size_t' (aka 'unsigned long') can be declared 'const'
[warning] 356-356: src/zx/FunctionalityConstruction.cpp:356:5 [misc-const-correctness]
variable 'nextControl' of type 'Qubit' (aka 'int') can be declared 'const'
[warning] 339-339: src/zx/FunctionalityConstruction.cpp:339:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
[warning] 336-336: src/zx/FunctionalityConstruction.cpp:336:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
🔇 Additional comments (7)
test/zx/test_zx_functionality.cpp (1)
232-359: Excellent test coverage for multi-control operations.The new tests comprehensively validate CRZ, MCX, and MCRZ operations by constructing equivalent circuits and verifying they reduce to identity. The test pattern is consistent with existing tests in the file.
src/zx/FunctionalityConstruction.cpp (5)
310-330: CCZ implementation looks correct.The addCcz function implements a double-controlled Z gate by adapting the CCX decomposition to work in the Z-basis.
332-340: CRZ implementation is correct.The addCrz function correctly implements controlled-RZ using the standard decomposition. The CNOT operations with target as control are intentional and correct for this decomposition, despite the static analysis warning.
680-682: LGTM: Single-controlled RZ support.Correctly handles controlled-RZ gates by delegating to the new addCrz function.
723-740: LGTM: Double-controlled gate support.The updated logic correctly handles CCZ and multi-controlled RZ operations with 2 controls by building a control vector and dispatching to the appropriate implementation functions.
741-762: LGTM: Multi-control gate support.The new branch properly handles gates with arbitrary numbers of controls, supporting MCX, MCZ, and MCRZ operations through the newly implemented functions.
include/mqt-core/zx/FunctionalityConstruction.hpp (1)
116-127: LGTM: Method declarations are well-structured.The new method declarations are consistent with existing patterns in the class and correctly match their implementations. Parameter types and const-correctness are appropriate.
Apply const to constant variables. Replace for loop with std::ranges::find_if implementation. Utilize static_cast to explicitly state conversion from unsigned to signed int. Shift return false of `transformableToZX` to be reachable again.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 2
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (1)
src/zx/FunctionalityConstruction.cpp(5 hunks)
🧰 Additional context used
🧠 Learnings (6)
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T18:19:31.857Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1679-1715
Timestamp: 2025-11-20T18:19:31.857Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the compareSwapAndBridge and compareShuttlingAndFlyingAncilla methods intentionally use division by zero to produce infinity when distance reductions are zero or negative. This infinity value marks that option as highly unfavorable in cost comparisons, which is the intended behavior rather than a bug.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-27T08:52:06.428Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1379-1383
Timestamp: 2025-11-27T08:52:06.428Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the getBestMovePos function throws std::runtime_error when no move position is found (finalBestPos.coords is empty). This behavior is acceptable for current use cases since tight architectures are not a concern. A future improvement would be to fall back to SWAP-based strategies instead of throwing.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
src/zx/FunctionalityConstruction.cpp
[warning] 395-395: src/zx/FunctionalityConstruction.cpp:395:9 [readability-else-after-return]
do not use 'else' after 'throw'
[warning] 339-339: src/zx/FunctionalityConstruction.cpp:339:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
[warning] 336-336: src/zx/FunctionalityConstruction.cpp:336:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
- GitHub Check: 🐍 Test (ubuntu-24.04) / 🐍 ubuntu-24.04
- GitHub Check: 🐍 Test (macos-14) / 🐍 macos-14
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
- GitHub Check: 🐍 Test (ubuntu-24.04-arm) / 🐍 ubuntu-24.04-arm
🔇 Additional comments (9)
src/zx/FunctionalityConstruction.cpp (9)
310-330: LGTM!The
addCczimplementation correctly decomposes the CCZ gate using standard T-gate decomposition. The Hadamard edges are appropriately placed at the end (compared toaddCcxwhich has them at start/end) since CCZ = H·CCX·H on the target.
342-364: DeclarenextControlas const.The variable
nextControlis not modified after initialization and should be declaredconst.- const Qubit nextControl = controls.back(); + const Qubit nextControl = controls.back();Note: This appears to already be addressed in the current code (line 356 shows
const). If the static analysis tool is still flagging this, the issue may be resolved.
424-449: LGTM!The
addMczfunction correctly implements multi-controlled Z using recursive decomposition with proper base cases for 0, 1, and 2 controls. ThenextControlvariable is already declaredconst.
682-684: LGTM!Correctly routes single-controlled RZ operations to the new
addCrzfunction.
725-742: LGTM!The two-control parsing correctly handles CCZ and MCRZ operations. The controls vector is appropriately constructed for the MCRZ case while maintaining backward compatibility with the existing CCX/CCZ signatures.
743-760: LGTM!The multi-control parsing branch correctly handles MCX, MCZ (via H·MCX·H decomposition), and MCRZ operations for gates with more than 2 controls. The Hadamard sandwiching for MCZ is the correct identity.
874-897: LGTM!The
transformableToZXfunction correctly extends support to recognize RZ operations in single-control, two-control, and multi-control contexts, consistent with the new parsing implementations.
416-419: DeclarelastControlas const.The variable
lastControlis not modified after initialization.- const Qubit lastControl = controls.back(); + const Qubit lastControl = controls.back();Note: Line 416 already shows
constin the provided code, so this may already be addressed.
382-384: Consider declaringfirstas const.The
firstvector is not modified after construction and could be declaredconstfor better const-correctness. Thesecondvector cannot be const since it's modified on line 399.const auto half = static_cast<std::ptrdiff_t>((controls.size() + 1) / 2); - const std::vector<Qubit> first(controls.begin(), controls.begin() + half); + const std::vector<Qubit> first(controls.begin(), controls.begin() + half); std::vector<Qubit> second(controls.begin() + half, controls.end());Note: Line 383 already shows
constin the provided code, so this appears to be addressed.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 2
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (1)
test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (3)
📓 Common learnings
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
test/zx/test_zx_functionality.cpp
🧬 Code graph analysis (1)
test/zx/test_zx_functionality.cpp (2)
src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(789-806)buildFunctionality(789-790)test/zx/test_simplify.cpp (1)
fullReduce(602-602)
🪛 Cppcheck (2.18.0)
test/zx/test_zx_functionality.cpp
[error] 269-269: syntax error
(syntaxError)
🔇 Additional comments (4)
test/zx/test_zx_functionality.cpp (4)
222-245: CRZ decomposition test is mathematically soundThe CRZ(π/2) vs CX–RZ(-π/4)–CX–RZ(π/4) equivalence is correct (exact, no global phase), and the functionality + reduction checks are appropriate for validating the new CRZ support.
247-268: MultiCZ equivalence to H–MCX–H is correctUsing
qc.mcz({1, 2}, 0)and comparing againsth(0); mcx({1, 2}, 0); h(0);is the standard construction for MCZ and should be functionally identical with zero global phase; the identity and phase checks nicely exercise the new MCZ path.
269-295: CCZ vs H–MCX–H construction is appropriateImporting
cczfrom OpenQASM and comparing it withh(0); mcx({1, 2}, 0); h(0);is a valid way to test CCZ support; this pattern realizes a three-qubit phase flip on |111⟩ with no extra global phase, so the identity and zero-global-phase expectations are well chosen.
296-383: Good coverage of MCX semantics across arities and decompositionsThe new MCX tests collectively cover:
- general MCX construction and inversion (
MultiControlX);- ancilla-based decomposition on a larger register (
MultiControlXLarger);- the degenerate 0-control case behaving as plain X (
MultiControlX0);- the 1-control case matching CX (
MultiControlX1).These are well-structured functionality checks for the new multi-control-X support.
3142193 to
9dee2a5
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 1
♻️ Duplicate comments (1)
test/zx/test_zx_functionality.cpp (1)
385-398: Consider strengthening connectivity assertions.The MCRZ test currently only checks connectivity for qubit 0. Following the pattern in
complexCircuit(lines 165-167), consider verifying connectivity for all involved qubits (0, 1, and 2) to catch potential wiring issues.Apply this diff to strengthen the test:
EXPECT_TRUE(d.isIdentity()); EXPECT_TRUE(d.globalPhaseIsZero()); EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); + EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); + EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2))); }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (2)
src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (10)
📓 Common learnings
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-24T10:19:41.147Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1326
File: python/mqt/core/__init__.py:22-22
Timestamp: 2025-11-24T10:19:41.147Z
Learning: In the munich-quantum-toolkit/core repository, Ruff is configured with 'ALL' rules enabled by default, and only specific rules are selectively disabled. When reviewing changes that enable previously-disabled rules (like PLC0415), noqa directives for those rules become necessary and should be retained.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-04T06:59:40.314Z
Learnt from: MatthiasReumann
Repo: munich-quantum-toolkit/core PR: 1301
File: mlir/lib/Dialect/MQTOpt/Transforms/Transpilation/LayeredUnit.cpp:84-85
Timestamp: 2025-12-04T06:59:40.314Z
Learning: In the MQTOpt MLIR routing passes (NaiveRoutingPassSC, AStarRoutingPassSC), the input IR is guaranteed to contain only 1-qubit and 2-qubit gates. All 3+-qubit gates must be decomposed before routing; otherwise the input IR is invalid. This invariant allows skipTwoQubitBlock in LayeredUnit.cpp to safely assert wires.size() == 2.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-11-01T15:57:31.153Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1283
File: src/qir/runtime/QIR.cpp:196-201
Timestamp: 2025-11-01T15:57:31.153Z
Learning: In the QIR runtime (src/qir/runtime/QIR.cpp), the PRX gate (__quantum__qis__prx__body) is an alias for the R gate (Phased X-Rotation) and should call runtime.apply<qc::R>(theta, phi, qubit), not runtime.apply<qc::RX>() which is a single-parameter rotation gate.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T23:16:16.276Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-101
Timestamp: 2025-12-08T23:16:16.276Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The CtrlInlineGPhase canonicalization pattern correctly only checks getNumPosControls() and processes only positive controls when inlining a GPhaseOp.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T18:19:31.857Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1679-1715
Timestamp: 2025-11-20T18:19:31.857Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the compareSwapAndBridge and compareShuttlingAndFlyingAncilla methods intentionally use division by zero to produce infinity when distance reductions are zero or negative. This infinity value marks that option as highly unfavorable in cost comparisons, which is the intended behavior rather than a bug.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🧬 Code graph analysis (1)
test/zx/test_zx_functionality.cpp (1)
src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(791-808)buildFunctionality(791-792)
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
test/zx/test_zx_functionality.cpp
[warning] 277-277: test/zx/test_zx_functionality.cpp:277:3 [misc-const-correctness]
variable 'diag' of type 'ZXDiagram' can be declared 'const'
src/zx/FunctionalityConstruction.cpp
[warning] 340-340: src/zx/FunctionalityConstruction.cpp:340:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
[warning] 337-337: src/zx/FunctionalityConstruction.cpp:337:3 [readability-suspicious-call-argument]
2nd argument 'target' (passed to 'ctrl') looks like it might be swapped with the 3rd, 'control' (passed to 'target')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
- GitHub Check: 🐍 Test (macos-14) / 🐍 macos-14
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
- GitHub Check: 🐍 Test (ubuntu-24.04) / 🐍 ubuntu-24.04
🔇 Additional comments (15)
test/zx/test_zx_functionality.cpp (6)
222-245: LGTM: CRZ test validates controlled-RZ decomposition.The test correctly verifies that the CRZ gate implementation matches the expected decomposition using CNOT and RZ gates, and properly checks identity, zero global phase, and connectivity after reduction.
247-268: LGTM: MultiCZ test validates multi-controlled Z construction.The test correctly verifies that MCZ is equivalent to H-MCX-H construction, with proper identity, phase, and connectivity checks.
296-315: LGTM: Multi-control X now supported.The test correctly validates that multi-controlled X gates (with 3 controls) are now transformable and produce identity when inverted, confirming the PR objective to add multi-control support.
317-339: LGTM: Ancilla-assisted MCX decomposition validated.The test correctly verifies the ancilla-assisted decomposition of MCX with 3 controls in a 5-qubit system, ensuring the decomposition is functionally equivalent.
341-361: LGTM: Edge case for 0-control MCX validated.The test correctly verifies that MCX with no controls reduces to a simple X gate.
363-383: LGTM: Edge case for 1-control MCX validated.The test correctly verifies that MCX with one control reduces to a CNOT gate.
src/zx/FunctionalityConstruction.cpp (9)
310-330: LGTM: CCZ implementation optimizes away redundant Hadamard edges.The
addCczfunction correctly implements a double-controlled Z gate by removing the initial and final Hadamard transformations from the CCX decomposition, providing an optimized construction as mentioned in the PR description.
332-341: LGTM: CRZ decomposition correctly implemented.The controlled-RZ decomposition correctly uses reversed CNOT direction (target→control) with appropriate phase factors (±θ/2), and includes a clarifying comment per previous review feedback.
343-365: LGTM: MCRZ recursive decomposition is correct.The multi-controlled RZ implementation correctly handles:
- Base case 0: Direct RZ spider
- Base case 1: CRZ
- Recursive case: Standard decomposition using CRZ(θ/2) interleaved with MCX to implement the controlled phase gate
The recursive pattern matches standard quantum computing decompositions.
367-424: LGTM: MCX decomposition handles all cases correctly.The multi-controlled X implementation properly handles:
- Base cases: 0 controls (X), 1 control (CNOT), 2 controls (CCX)
- Ancilla-assisted recursion when spare qubits are available
- No-ancilla decomposition using RX + MCZ pattern when qubits are fully utilized
The ancilla search logic and error handling were addressed in previous reviews. The divide-and-conquer strategy is correct.
426-451: LGTM: MCZ recursive decomposition is correct.The multi-controlled Z implementation correctly handles base cases (0, 1, 2 controls) and uses the standard recursive decomposition with CRZ(π/2) interleaved with MCX for larger control counts.
684-686: LGTM: RZ added to single-control routing.Correctly routes controlled-RZ operations through the new
addCrzfunction when a single control is present.
727-744: LGTM: Two-control branch extended for Z and RZ.The two-control branch now:
- Extracts controls into a vector for use by multi-control functions
- Routes CCZ through
addCcz- Routes CCRZ through
addMcrzThis correctly extends the transformation capabilities for double-controlled gates.
745-766: LGTM: Multi-control branch handles X, Z, and RZ.The new multi-control branch (3+ controls, single target) correctly:
- Routes MCX through
addMcx- Routes MCZ through H-MCX-H pattern
- Routes MCRZ through
addMcrz- Throws for unsupported operations
This implements the core PR objective of supporting multi-controlled gates.
866-899: LGTM: transformableToZX correctly updated for RZ support.The
transformableToZXfunction now correctly recognizes RZ as transformable in:
- Single-control scenarios (line 876)
- Two-control scenarios (line 886)
- Multi-control scenarios (line 895)
This aligns with the new routing logic in
parseOpand fulfills the PR objective.
1d008c6 to
ccaf44d
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 1
♻️ Duplicate comments (1)
src/zx/FunctionalityConstruction.cpp (1)
332-341: About the suspiciousaddCrzargument order warningsStatic analysis flags the calls to
addCrzas “suspicious call argument” because the function signature isvoid FunctionalityConstruction::addCrz( ZXDiagram& diag, const PiExpression& phase, const Qubit target, const Qubit control, std::vector<Vertex>& qubits)while call sites conceptually pass
(control, target).Given the body:
// CRZ decomposition uses reversed CNOT direction addCnot(diag, control, target, qubits); addZSpider(diag, target, qubits, -phase / 2); addZSpider(diag, control, qubits, phase / 2); addCnot(diag, control, target, qubits);and how it’s invoked from
parseOpand the multi-control helpers, the effective semantics are consistent with the intended CRZ decomposition (as validated by the new CRZ / MCRZ tests). The warnings are therefore a readability issue rather than a correctness bug.If you want to silence the tools and make the intent clearer, consider flipping the parameter names/order to
(const Qubit control, const Qubit target)and updating the call sites accordingly, so callers and implementation agree on ordering and static analysis no longer complains.Also applies to: 360-363, 446-448, 684-686
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (2)
src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (12)
📓 Common learnings
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Learnt from: MatthiasReumann
Repo: munich-quantum-toolkit/core PR: 1301
File: mlir/lib/Dialect/MQTOpt/Transforms/Transpilation/LayeredUnit.cpp:84-85
Timestamp: 2025-12-04T06:59:40.314Z
Learning: In the MQTOpt MLIR routing passes (NaiveRoutingPassSC, AStarRoutingPassSC), the input IR is guaranteed to contain only 1-qubit and 2-qubit gates. All 3+-qubit gates must be decomposed before routing; otherwise the input IR is invalid. This invariant allows skipTwoQubitBlock in LayeredUnit.cpp to safely assert wires.size() == 2.
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
src/zx/FunctionalityConstruction.cpptest/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-08T23:58:03.684Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:80-100
Timestamp: 2025-12-08T23:58:03.684Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), quartz.ctrl uses reference semantics and does not return values, unlike flux.ctrl which uses value semantics and returns transformed qubits. When inlining a GPhaseOp in the CtrlInlineGPhase pattern, it's correct to create POp operations for positive controls and erase the CtrlOp without collecting or replacing result values.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
src/zx/FunctionalityConstruction.cpptest/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-08T23:16:16.276Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-101
Timestamp: 2025-12-08T23:16:16.276Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The CtrlInlineGPhase canonicalization pattern correctly only checks getNumPosControls() and processes only positive controls when inlining a GPhaseOp.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T18:19:31.857Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1679-1715
Timestamp: 2025-11-20T18:19:31.857Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the compareSwapAndBridge and compareShuttlingAndFlyingAncilla methods intentionally use division by zero to produce infinity when distance reductions are zero or negative. This infinity value marks that option as highly unfavorable in cost comparisons, which is the intended behavior rather than a bug.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-01T15:57:31.153Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1283
File: src/qir/runtime/QIR.cpp:196-201
Timestamp: 2025-11-01T15:57:31.153Z
Learning: In the QIR runtime (src/qir/runtime/QIR.cpp), the PRX gate (__quantum__qis__prx__body) is an alias for the R gate (Phased X-Rotation) and should call runtime.apply<qc::R>(theta, phi, qubit), not runtime.apply<qc::RX>() which is a single-parameter rotation gate.
Applied to files:
src/zx/FunctionalityConstruction.cpptest/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-24T10:19:41.147Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1326
File: python/mqt/core/__init__.py:22-22
Timestamp: 2025-11-24T10:19:41.147Z
Learning: In the munich-quantum-toolkit/core repository, Ruff is configured with 'ALL' rules enabled by default, and only specific rules are selectively disabled. When reviewing changes that enable previously-disabled rules (like PLC0415), noqa directives for those rules become necessary and should be retained.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-04T06:59:40.314Z
Learnt from: MatthiasReumann
Repo: munich-quantum-toolkit/core PR: 1301
File: mlir/lib/Dialect/MQTOpt/Transforms/Transpilation/LayeredUnit.cpp:84-85
Timestamp: 2025-12-04T06:59:40.314Z
Learning: In the MQTOpt MLIR routing passes (NaiveRoutingPassSC, AStarRoutingPassSC), the input IR is guaranteed to contain only 1-qubit and 2-qubit gates. All 3+-qubit gates must be decomposed before routing; otherwise the input IR is invalid. This invariant allows skipTwoQubitBlock in LayeredUnit.cpp to safely assert wires.size() == 2.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-11-20T16:57:24.305Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: test/hybridmap/test_hybridmap.cpp:200-287
Timestamp: 2025-11-20T16:57:24.305Z
Learning: In test/hybridmap/test_hybridmap.cpp, the LongShuttling test is designed as a stress test to catch rare edge cases that only occur after extended shuttling sequences, which is why it maps a long circuit without explicit assertions beyond ensuring no exceptions are thrown.
Applied to files:
test/zx/test_zx_functionality.cpp
🧬 Code graph analysis (1)
test/zx/test_zx_functionality.cpp (2)
include/mqt-core/zx/FunctionalityConstruction.hpp (2)
qc(39-39)qc(50-50)src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(791-808)buildFunctionality(791-792)
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
src/zx/FunctionalityConstruction.cpp
[warning] 448-448: src/zx/FunctionalityConstruction.cpp:448:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 446-446: src/zx/FunctionalityConstruction.cpp:446:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 362-362: src/zx/FunctionalityConstruction.cpp:362:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 360-360: src/zx/FunctionalityConstruction.cpp:360:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 685-685: src/zx/FunctionalityConstruction.cpp:685:7 [readability-suspicious-call-argument]
3rd argument 'ctrl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: 🐍 Test (ubuntu-24.04) / 🐍 ubuntu-24.04
- GitHub Check: 🐍 Test (macos-14) / 🐍 macos-14
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
🔇 Additional comments (3)
test/zx/test_zx_functionality.cpp (1)
222-505: New multi-control ZX tests look correct and give solid coverageThe CRZ, CCZ, MCX/MCZ, and MCRZ tests follow the existing testing pattern (build both circuits, compose with inverse, reduce, then check identity/global phase/connectivity) and cover:
- 0/1/2/many controls for X, Z, and RZ;
- both direct constructions (mcz/mcx/mcrz/crz) and decompositions via standard gates (CX, H, RZ).
I don’t see functional or structural issues here; these should give good end‑to‑end coverage of the new functionality.
src/zx/FunctionalityConstruction.cpp (2)
310-365: Multi-control CCZ / CRZ / MCRZ / MCZ decompositions look structurally soundThe new helpers
addCcz(two controls, Z-like),addCrz(controlled-RZ),addMcrz(multi-controlled RZ, with 0/1-control base cases and recursive step),addMcz(multi-controlled Z with 0/1/2-control base cases and recursive step),are consistent with known constructions:
- Base cases (0 controls → single-qubit gate, 1 control → CRZ, 2 controls → CCZ) are explicit.
- Recursive branches always shrink
controls(viacontrols.pop_back()), so the recursion terminates.- The CRZ helper is reused in both the single-control path (in
parseOp) and the multi-control decompositions, keeping the semantics aligned.- Tests exercise CRZ, CCZ, MCRZ (including k=0/1 and k>1), and MCZ (including k=0/1/2 and larger), and also check global-phase cancellation.
Given that and the existing ZX primitives, the design here looks correct and maintainable.
Also applies to: 426-451
661-767:parseOpandtransformableToZXextensions for controlled RZ and multi-control gates are consistentThe changes in:
parseOp:
- add a
qc::OpType::RZcase for 1-control/1-target gates usingaddCrz;- route 2-control RZ to
addMcrzwith a 2-element controls vector;- route general multi-control X/Z/RZ (one target) to
addMcx, the CZ-styleH–MCX–Hpattern, andaddMcrzrespectively.
transformableToZX:
- include
qc::OpType::RZin the supported sets for
- uncontrolled single-qubit,
- single-control two-qubit, and
- multi-control single-target operations,
are aligned: every newly-routed case has a corresponding “supported” entry, and unsupported multi-control types still fall through to the existing exceptions (as exercised by the
UnsupportedControltests).I don’t see missing or inconsistent cases here.
Also applies to: 876-899
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 1
♻️ Duplicate comments (1)
src/zx/FunctionalityConstruction.cpp (1)
332-341: Consider swapping parameter names to match codebase convention.The parameter order
(target, control)differs from the convention used elsewhere in this file (e.g.,addCnot,addCphaseuse(ctrl, target)). This triggers persistent static analysis warnings at every call site (lines 354, 360, 362, 436, 446, 448, 685).While the comment clarifies the decomposition intent, renaming the parameters would eliminate linter noise and improve readability.
void FunctionalityConstruction::addCrz(ZXDiagram& diag, const PiExpression& phase, - const Qubit target, const Qubit control, + const Qubit ctrl, const Qubit target, std::vector<Vertex>& qubits) { // CRZ decomposition uses reversed CNOT direction - addCnot(diag, control, target, qubits); - addZSpider(diag, target, qubits, -phase / 2); - addZSpider(diag, control, qubits, phase / 2); - addCnot(diag, control, target, qubits); + addCnot(diag, target, ctrl, qubits); + addZSpider(diag, ctrl, qubits, -phase / 2); + addZSpider(diag, target, qubits, phase / 2); + addCnot(diag, target, ctrl, qubits); }This would require updating all call sites to swap arguments accordingly.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (2)
src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (10)
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-24T10:19:41.147Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1326
File: python/mqt/core/__init__.py:22-22
Timestamp: 2025-11-24T10:19:41.147Z
Learning: In the munich-quantum-toolkit/core repository, Ruff is configured with 'ALL' rules enabled by default, and only specific rules are selectively disabled. When reviewing changes that enable previously-disabled rules (like PLC0415), noqa directives for those rules become necessary and should be retained.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T16:57:24.305Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: test/hybridmap/test_hybridmap.cpp:200-287
Timestamp: 2025-11-20T16:57:24.305Z
Learning: In test/hybridmap/test_hybridmap.cpp, the LongShuttling test is designed as a stress test to catch rare edge cases that only occur after extended shuttling sequences, which is why it maps a long circuit without explicit assertions beyond ensuring no exceptions are thrown.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-08T23:58:03.684Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:80-100
Timestamp: 2025-12-08T23:58:03.684Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), quartz.ctrl uses reference semantics and does not return values, unlike flux.ctrl which uses value semantics and returns transformed qubits. When inlining a GPhaseOp in the CtrlInlineGPhase pattern, it's correct to create POp operations for positive controls and erase the CtrlOp without collecting or replacing result values.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T23:16:16.276Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-101
Timestamp: 2025-12-08T23:16:16.276Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The CtrlInlineGPhase canonicalization pattern correctly only checks getNumPosControls() and processes only positive controls when inlining a GPhaseOp.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T18:19:31.857Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1679-1715
Timestamp: 2025-11-20T18:19:31.857Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the compareSwapAndBridge and compareShuttlingAndFlyingAncilla methods intentionally use division by zero to produce infinity when distance reductions are zero or negative. This infinity value marks that option as highly unfavorable in cost comparisons, which is the intended behavior rather than a bug.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-01T15:57:31.153Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1283
File: src/qir/runtime/QIR.cpp:196-201
Timestamp: 2025-11-01T15:57:31.153Z
Learning: In the QIR runtime (src/qir/runtime/QIR.cpp), the PRX gate (__quantum__qis__prx__body) is an alias for the R gate (Phased X-Rotation) and should call runtime.apply<qc::R>(theta, phi, qubit), not runtime.apply<qc::RX>() which is a single-parameter rotation gate.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🧬 Code graph analysis (2)
test/zx/test_zx_functionality.cpp (2)
include/mqt-core/zx/FunctionalityConstruction.hpp (2)
qc(39-39)qc(50-50)src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(791-808)buildFunctionality(791-792)
src/zx/FunctionalityConstruction.cpp (2)
include/mqt-core/ir/operations/OpType.hpp (1)
toString(40-40)src/ir/operations/OpType.cpp (2)
toString(21-35)toString(21-21)
🪛 GitHub Check: 🇨 Lint / 🚨 Lint
src/zx/FunctionalityConstruction.cpp
[warning] 448-448: src/zx/FunctionalityConstruction.cpp:448:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 446-446: src/zx/FunctionalityConstruction.cpp:446:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 362-362: src/zx/FunctionalityConstruction.cpp:362:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 360-360: src/zx/FunctionalityConstruction.cpp:360:5 [readability-suspicious-call-argument]
3rd argument 'nextControl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
[warning] 685-685: src/zx/FunctionalityConstruction.cpp:685:7 [readability-suspicious-call-argument]
3rd argument 'ctrl' (passed to 'target') looks like it might be swapped with the 4th, 'target' (passed to 'control')
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: 🐍 Test (windows-2022) / 🐍 windows-2022
- GitHub Check: 🐍 Test (macos-15-intel) / 🐍 macos-15-intel
🔇 Additional comments (13)
src/zx/FunctionalityConstruction.cpp (6)
310-330: LGTM: CCZ decomposition correctly optimizes away Hadamard bookends.The
addCczimplementation is a well-optimized variant of CCX that directly produces the CCZ decomposition. Compared toaddCcx, it removes the opening H gate and adjusts the closing sequence to use an H-edge followed by another H-edge, which correctly implements CCZ = H(target) · CCX · H(target) in a more efficient ZX form.
343-365: LGTM: MCRZ recursive decomposition is correct.The implementation correctly handles base cases (0 and 1 controls) and uses the standard recursive decomposition: CRZ(θ/2) · MCX · CRZ(-θ/2) · MCX for extracting one control at a time.
367-424: LGTM: MCX decomposition with ancilla-based optimization.The implementation correctly handles all base cases and provides two decomposition paths:
- When ancilla qubits are available: efficient divide-and-conquer using the spare qubit
- When no ancilla available: RX-based decomposition using MCZ and MCRZ
Previous review issues (uninitialized
anc, missing error check) have been properly addressed.
426-451: LGTM: MCZ recursive decomposition is correct.The implementation properly handles all base cases including the use of
addCczfor 2 controls (which is more efficient than the general recursion). The recursive decomposition follows the standard pattern.
684-686: LGTM: parseOp correctly routes multi-control operations to new handlers.The integration properly:
- Routes single-control RZ to
addCrz- Builds control vectors from operation controls for 2+ control cases
- Delegates to
addMcrz,addMcx,addMczas appropriateThe static analysis warning on line 685 is the same
addCrzparameter naming issue noted earlier.Also applies to: 727-744, 745-766
876-900: LGTM: transformableToZX correctly updated for new multi-control gates.The transformability checks now properly reflect the expanded parseOp capabilities, allowing RZ in single-control, 2-control, and arbitrary multi-control contexts.
test/zx/test_zx_functionality.cpp (7)
222-245: LGTM: CRZ test properly validates against known decomposition.The test correctly validates CRZ by comparing against the explicit decomposition: CNOT · RZ(-θ/2) · CNOT · RZ(θ/2).
247-268: LGTM: MultiCZ test validates against H·MCX·H equivalence.Correct validation that MCZ equals H·MCX·H on the target qubit.
269-293: LGTM: CCZ test validates correctly.Past review issue (unused
diagvariable) has been addressed.
316-338: LGTM: Proper validation against ancilla-based decomposition.This test correctly validates the MCX decomposition by comparing against the explicit ancilla-based construction that the implementation uses internally.
340-382: LGTM: Boundary cases for MCX properly tested.
MultiControlX0validates 0-control MCX equals X, andMultiControlX1validates 1-control MCX equals CNOT. These are important boundary condition tests.
384-449: LGTM: Comprehensive MCZ test coverage.The tests properly validate:
MultiControlZ: MCZ equals H·MCX·HMultiControlZ0: 0-control MCZ equals ZMultiControlZ1: 1-control MCZ equals CZGood coverage of boundary conditions and correct equivalences.
451-506: LGTM: MCRZ tests cover self-inverse and boundary cases.The tests validate:
MultiControlRZ: MCRZ(θ) · MCRZ(-θ) = I (self-inverse property)MultiControlRZ0: 0-control MCRZ equals RZMultiControlRZ1: 1-control MCRZ equals CRZGood boundary condition coverage.
Co-authored-by: Copilot <[email protected]> Signed-off-by: Marcel Walter <[email protected]>
ba1071f to
0911f7c
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 8
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (2)
src/zx/FunctionalityConstruction.cpp(5 hunks)test/zx/test_zx_functionality.cpp(1 hunks)
🧰 Additional context used
🧠 Learnings (10)
📚 Learning: 2025-12-08T12:44:05.874Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:60-70
Timestamp: 2025-12-08T12:44:05.874Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The RemoveTrivialCtrl pattern correctly only checks getNumPosControls() when determining if a CtrlOp should be removed.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:13:51.224Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/lib/Dialect/MQTOpt/Transforms/ReplaceBasisStateControlsWithIfPattern.cpp:171-180
Timestamp: 2025-10-09T13:13:51.224Z
Learning: In MQT Core MLIR, UnitaryInterface operations guarantee 1-1 correspondence between input and output qubits in the same order. When cloning or modifying unitary operations (e.g., removing controls), this correspondence is maintained by construction, so yielding getAllInQubits() in else-branches matches the result types from the operation's outputs.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-10-09T13:20:11.483Z
Learnt from: DRovara
Repo: munich-quantum-toolkit/core PR: 1108
File: mlir/test/Dialect/MQTOpt/Transforms/lift-measurements.mlir:269-288
Timestamp: 2025-10-09T13:20:11.483Z
Learning: In the MQT MLIR dialect, the `rz` gate should not be included in the `DIAGONAL_GATES` set for the `ReplaceBasisStateControlsWithIfPattern` because its operator matrix does not have the required shape | 1 0 | / | 0 x | for the targets-as-controls optimization. It is only included in `LiftMeasurementsAboveGatesPatterns` where the matrix structure requirement differs.
Applied to files:
test/zx/test_zx_functionality.cppsrc/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T16:57:24.305Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: test/hybridmap/test_hybridmap.cpp:200-287
Timestamp: 2025-11-20T16:57:24.305Z
Learning: In test/hybridmap/test_hybridmap.cpp, the LongShuttling test is designed as a stress test to catch rare edge cases that only occur after extended shuttling sequences, which is why it maps a long circuit without explicit assertions beyond ensuring no exceptions are thrown.
Applied to files:
test/zx/test_zx_functionality.cpp
📚 Learning: 2025-12-08T23:58:03.684Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp:80-100
Timestamp: 2025-12-08T23:58:03.684Z
Learning: In the Quartz dialect (mlir/lib/Dialect/Quartz/IR/Modifiers/CtrlOp.cpp), quartz.ctrl uses reference semantics and does not return values, unlike flux.ctrl which uses value semantics and returns transformed qubits. When inlining a GPhaseOp in the CtrlInlineGPhase pattern, it's correct to create POp operations for positive controls and erase the CtrlOp without collecting or replacing result values.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T23:16:16.276Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-101
Timestamp: 2025-12-08T23:16:16.276Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), negative controls are not supported at the current stage. The CtrlInlineGPhase canonicalization pattern correctly only checks getNumPosControls() and processes only positive controls when inlining a GPhaseOp.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-20T18:19:31.857Z
Learnt from: lsschmid
Repo: munich-quantum-toolkit/qmap PR: 832
File: src/hybridmap/HybridNeutralAtomMapper.cpp:1679-1715
Timestamp: 2025-11-20T18:19:31.857Z
Learning: In src/hybridmap/HybridNeutralAtomMapper.cpp, the compareSwapAndBridge and compareShuttlingAndFlyingAncilla methods intentionally use division by zero to produce infinity when distance reductions are zero or negative. This infinity value marks that option as highly unfavorable in cost comparisons, which is the intended behavior rather than a bug.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-11-01T15:57:31.153Z
Learnt from: burgholzer
Repo: munich-quantum-toolkit/core PR: 1283
File: src/qir/runtime/QIR.cpp:196-201
Timestamp: 2025-11-01T15:57:31.153Z
Learning: In the QIR runtime (src/qir/runtime/QIR.cpp), the PRX gate (__quantum__qis__prx__body) is an alias for the R gate (Phased X-Rotation) and should call runtime.apply<qc::R>(theta, phi, qubit), not runtime.apply<qc::RX>() which is a single-parameter rotation gate.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-04T06:59:40.314Z
Learnt from: MatthiasReumann
Repo: munich-quantum-toolkit/core PR: 1301
File: mlir/lib/Dialect/MQTOpt/Transforms/Transpilation/LayeredUnit.cpp:84-85
Timestamp: 2025-12-04T06:59:40.314Z
Learning: In the MQTOpt MLIR routing passes (NaiveRoutingPassSC, AStarRoutingPassSC), the input IR is guaranteed to contain only 1-qubit and 2-qubit gates. All 3+-qubit gates must be decomposed before routing; otherwise the input IR is invalid. This invariant allows skipTwoQubitBlock in LayeredUnit.cpp to safely assert wires.size() == 2.
Applied to files:
src/zx/FunctionalityConstruction.cpp
📚 Learning: 2025-12-08T14:55:43.880Z
Learnt from: denialhaag
Repo: munich-quantum-toolkit/core PR: 1264
File: mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp:78-100
Timestamp: 2025-12-08T14:55:43.880Z
Learning: In the Flux dialect (mlir/lib/Dialect/Flux/IR/Modifiers/CtrlOp.cpp), GPhaseOp is a zero-target operation (global phase). When a CtrlOp wraps a GPhaseOp, it only has control qubits and no targets. The CtrlInlineGPhase canonicalization pattern correctly produces outputs only for the positive controls, not targets.
Applied to files:
src/zx/FunctionalityConstruction.cpp
🧬 Code graph analysis (2)
test/zx/test_zx_functionality.cpp (2)
include/mqt-core/zx/FunctionalityConstruction.hpp (2)
qc(39-39)qc(50-50)src/zx/FunctionalityConstruction.cpp (2)
buildFunctionality(792-809)buildFunctionality(792-793)
src/zx/FunctionalityConstruction.cpp (2)
include/mqt-core/ir/operations/OpType.hpp (1)
toString(40-40)src/ir/operations/OpType.cpp (2)
toString(21-35)toString(21-21)
🔇 Additional comments (8)
test/zx/test_zx_functionality.cpp (2)
318-340: LGTM! Strong validation using ancilla decomposition.This test validates MCX against an ancilla-based decomposition, which is a more robust verification than self-inverse. Consider adding connectivity checks for all 5 qubits for completeness.
342-362: LGTM!Good edge case coverage testing MCX with zero controls, verifying it reduces to a simple X gate.
src/zx/FunctionalityConstruction.cpp (6)
310-330: LGTM!The CCZ implementation correctly uses a T-gate decomposition. The structure appropriately omits the initial Hadamard from the CCX decomposition while maintaining the necessary phase structure, with the final Hadamard edges properly placed.
332-341: LGTM!The CRZ implementation uses the correct decomposition formula with the intentional CNOT direction reversal properly documented.
343-365: LGTM!The MCRZ implementation correctly uses recursive decomposition with proper base cases. The
controlsvector is appropriately passed by value to allow modification without affecting the caller.
367-425: LGTM!The MCX implementation handles base cases correctly and uses two decomposition strategies depending on ancilla availability. The ancilla selection now properly iterates over qubit indices rather than vertex values (addressing the previous critical issue).
427-452: LGTM!The MCZ implementation correctly uses recursive decomposition with proper base cases for 0, 1, and 2 controls.
877-900: LGTM!The
transformableToZXfunction is correctly updated to recognize RZ gates in all control configurations (1, 2, and 3+ controls), matching the correspondingparseOpimplementations.
| std::vector<Qubit> controls; | ||
| for (const auto& ctrl : op->getControls()) { | ||
| controls.push_back(static_cast<Qubit>(p.at(ctrl.qubit))); | ||
| } | ||
| switch (op->getType()) { | ||
| case qc::OpType::X: | ||
| addCcx(diag, ctrl0, ctrl1, target, qubits); | ||
| break; | ||
|
|
||
| case qc::OpType::Z: | ||
| addCcz(diag, ctrl0, ctrl1, target, qubits); | ||
| break; | ||
| case qc::OpType::RZ: | ||
| addMcrz(diag, parseParam(op.get(), 0), controls, target, qubits); | ||
| break; | ||
| default: | ||
| throw ZXException("Unsupported Multi-control operation: " + | ||
| qc::toString(op->getType())); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Unused controls vector in 2-control branch.
The controls vector is constructed at lines 728-731 but is only used for the RZ case at line 740. For X and Z cases, ctrl0 and ctrl1 are used directly. This is not a bug but introduces slight redundancy.
Consider constructing controls only when needed, or using it consistently for all cases:
+ // Build controls vector for multi-control dispatch
std::vector<Qubit> controls;
for (const auto& ctrl : op->getControls()) {
controls.push_back(static_cast<Qubit>(p.at(ctrl.qubit)));
}
switch (op->getType()) {
case qc::OpType::X:
- addCcx(diag, ctrl0, ctrl1, target, qubits);
+ addCcx(diag, controls.front(), controls.back(), target, qubits);
break;
case qc::OpType::Z:
- addCcz(diag, ctrl0, ctrl1, target, qubits);
+ addCcz(diag, controls.front(), controls.back(), target, qubits);
break;🤖 Prompt for AI Agents
In src/zx/FunctionalityConstruction.cpp around lines 728-745 the vector controls
is populated unconditionally but only used in the RZ branch; avoid the
redundancy by moving the construction into the RZ case (or alternately use the
controls vector for all branches). Update the code so that controls is
declared/filled only inside the qc::OpType::RZ case before calling addMcrz(diag,
parseParam(op.get(), 0), controls, target, qubits), and remove the unused
controls construction from before the switch; ensure no other branches depend on
controls.
| TEST_F(ZXFunctionalityTest, CRZ) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(2); | ||
| qc.crz(PI / 2, 0, 1); | ||
|
|
||
| auto qcPrime = qc::QuantumComputation(2); | ||
|
|
||
| qcPrime.cx(0, 1); | ||
| qcPrime.rz(-PI / 4, 1); | ||
| qcPrime.cx(0, 1); | ||
| qcPrime.rz(PI / 4, 1); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertion for qubit 1.
The test validates CRZ correctness but only checks connectivity for qubit 0. For completeness, add a connectivity check for qubit 1 to ensure both wires are properly connected after reduction.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 222 to 245, the test verifies
CRZ but only asserts connectivity for qubit 0; add an assertion that qubit 1 is
also connected after reduction. Insert a check like
EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); immediately after the
existing connectivity assertion for qubit 0 so both wires are validated.
| TEST_F(ZXFunctionalityTest, MultiCZ) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(3); | ||
| qc.mcz({1, 2}, 0); | ||
|
|
||
| auto qcPrime = qc::QuantumComputation(3); | ||
| qcPrime.h(0); | ||
| qcPrime.mcx({1, 2}, 0); | ||
| qcPrime.h(0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertions for all qubits.
For a 3-qubit test, only qubit 0's connectivity is verified. Add checks for qubits 1 and 2 for comprehensive validation.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
+ EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 247 to 268, the test currently
only asserts connectivity for qubit 0 after reduction; add analogous
connectivity assertions for qubits 1 and 2 (i.e., call
EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))) and
EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)))) so all three qubits are
validated.
| TEST_F(ZXFunctionalityTest, CCZ) { | ||
| using namespace qc::literals; | ||
| const std::string testfile = "OPENQASM 2.0;" | ||
| "include \"qelib1.inc\";" | ||
| "qreg q[3];" | ||
| "ccz q[0],q[1],q[2];\n"; | ||
|
|
||
| qc = qasm3::Importer::imports(testfile); | ||
| auto qcPrime = qc::QuantumComputation(3); | ||
| qcPrime.h(0); | ||
| qcPrime.mcx({1, 2}, 0); | ||
| qcPrime.h(0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertions for all qubits.
Similar to other 3-qubit tests, add connectivity checks for qubits 1 and 2.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
+ EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| TEST_F(ZXFunctionalityTest, CCZ) { | |
| using namespace qc::literals; | |
| const std::string testfile = "OPENQASM 2.0;" | |
| "include \"qelib1.inc\";" | |
| "qreg q[3];" | |
| "ccz q[0],q[1],q[2];\n"; | |
| qc = qasm3::Importer::imports(testfile); | |
| auto qcPrime = qc::QuantumComputation(3); | |
| qcPrime.h(0); | |
| qcPrime.mcx({1, 2}, 0); | |
| qcPrime.h(0); | |
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | |
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | |
| d.concat(dPrime.invert()); | |
| fullReduce(d); | |
| EXPECT_TRUE(d.isIdentity()); | |
| EXPECT_TRUE(d.globalPhaseIsZero()); | |
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | |
| } | |
| TEST_F(ZXFunctionalityTest, CCZ) { | |
| using namespace qc::literals; | |
| const std::string testfile = "OPENQASM 2.0;" | |
| "include \"qelib1.inc\";" | |
| "qreg q[3];" | |
| "ccz q[0],q[1],q[2];\n"; | |
| qc = qasm3::Importer::imports(testfile); | |
| auto qcPrime = qc::QuantumComputation(3); | |
| qcPrime.h(0); | |
| qcPrime.mcx({1, 2}, 0); | |
| qcPrime.h(0); | |
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | |
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | |
| d.concat(dPrime.invert()); | |
| fullReduce(d); | |
| EXPECT_TRUE(d.isIdentity()); | |
| EXPECT_TRUE(d.globalPhaseIsZero()); | |
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | |
| EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); | |
| EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2))); | |
| } |
🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 269 to 293, the test only
asserts connectivity for qubit 0; add connectivity assertions for qubits 1 and 2
as well. After the existing EXPECT_TRUE(d.connected(d.getInput(0),
d.getOutput(0))); line, add equivalent assertions for inputs/outputs 1 and 2
(i.e., EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); and
EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));) so all three qubits
are checked for connectivity.
| TEST_F(ZXFunctionalityTest, MultiControlX) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(4); | ||
| qc.mcx({1, 2, 3}, 0); | ||
| EXPECT_FALSE(FunctionalityConstruction::transformableToZX(&qc)); | ||
| EXPECT_THROW(const ZXDiagram diag = | ||
| FunctionalityConstruction::buildFunctionality(&qc), | ||
| ZXException); | ||
|
|
||
| auto qcPrime = qc::QuantumComputation(4); | ||
| qcPrime.h(0); | ||
| qcPrime.mcz({1, 2, 3}, 0); | ||
| qcPrime.h(0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertions for all qubits.
For a 4-qubit test, verify connectivity for all qubits 0-3.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
+ EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));
+ EXPECT_TRUE(d.connected(d.getInput(3), d.getOutput(3)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 295-316, the test currently
asserts connectivity only for qubit 0; add assertions that verify connectivity
for all 4 qubits (0–3). Modify the test to check d.connected(d.getInput(i),
d.getOutput(i)) for i in 0..3 (either by adding three additional EXPECT_TRUE
calls for 1,2,3 or a small loop generating those EXPECT_TRUE assertions) so
every input/output qubit pair is asserted connected.
| TEST_F(ZXFunctionalityTest, MultiControlX1) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(2); | ||
| qc.mcx({1}, 0); | ||
|
|
||
| auto qcPrime = qc::QuantumComputation(2); | ||
|
|
||
| qcPrime.cx(1, 0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertion for qubit 1.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 364 to 384, the test currently
asserts connectivity for qubit 0 only; add an assertion to verify qubit 1 is
also connected after construction, reduction, and concatenation. Insert a line
similar to EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); immediately
after the existing connectivity check for qubit 0 so the test validates
connectivity for both qubits.
| TEST_F(ZXFunctionalityTest, MultiControlZ) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(4); | ||
| qc.mcz({1, 2, 3}, 0); | ||
|
|
||
| auto qcPrime = qc::QuantumComputation(4); | ||
| qcPrime.h(0); | ||
| qcPrime.mcx({1, 2, 3}, 0); | ||
| qcPrime.h(0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| auto dPrime = FunctionalityConstruction::buildFunctionality(&qcPrime); | ||
|
|
||
| d.concat(dPrime.invert()); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1))); | ||
| EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertion for qubit 3.
The test correctly checks connectivity for qubits 0-2 but misses qubit 3.
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));
+ EXPECT_TRUE(d.connected(d.getInput(3), d.getOutput(3)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 386 to 409, the test checks
connectivity for qubits 0–2 but omits qubit 3; add an assertion verifying
d.connected(d.getInput(3), d.getOutput(3)) (similar style to the existing
checks) near the other EXPECT_TRUE connectivity assertions so all four qubits
are validated.
| TEST_F(ZXFunctionalityTest, MultiControlRZ) { | ||
| using namespace qc::literals; | ||
| qc = qc::QuantumComputation(3); | ||
| qc.mcrz(PI / 4, {1, 2}, 0); | ||
| qc.mcrz(-PI / 4, {1, 2}, 0); | ||
|
|
||
| auto d = FunctionalityConstruction::buildFunctionality(&qc); | ||
|
|
||
| fullReduce(d); | ||
|
|
||
| EXPECT_TRUE(d.isIdentity()); | ||
| EXPECT_TRUE(d.globalPhaseIsZero()); | ||
| EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0))); | ||
| } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧹 Nitpick | 🔵 Trivial
Add connectivity assertions for qubits 1 and 2.
The MultiControlRZ test uses 3 qubits but only checks qubit 0's connectivity.
EXPECT_TRUE(d.isIdentity());
EXPECT_TRUE(d.globalPhaseIsZero());
EXPECT_TRUE(d.connected(d.getInput(0), d.getOutput(0)));
+ EXPECT_TRUE(d.connected(d.getInput(1), d.getOutput(1)));
+ EXPECT_TRUE(d.connected(d.getInput(2), d.getOutput(2)));
}🤖 Prompt for AI Agents
In test/zx/test_zx_functionality.cpp around lines 453 to 466, the MultiControlRZ
test builds a 3-qubit functionality but only asserts connectivity for qubit 0;
add assertions to verify qubit 1 and qubit 2 are connected similarly to qubit 0
(call d.connected(d.getInput(1), d.getOutput(1)) and d.connected(d.getInput(2),
d.getOutput(2))), keeping them as EXPECT_TRUE checks after the existing
connectivity assertion so the test validates all three qubits.
Description
Add CRZ, MCX, MCZ, MCRZ functionality to ZX package.
Add convenience addCCZ function as it avoids one additional Hardamard edge (optimizes it away).
Fixes #1357
Checklist: